On the use of the transient information for gas identification using microelectronic gas sensor

Sofiane Brahim-Belhouari, Amine Bermak, Guangfen Wei, Philip C H Chan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Gas identification using microelectronic gas sensor represents a big challenge for pattern recognition systems due to a number of problems mainly related to non-selectivity and the drift. The use of preprocessing can often greatly improve the recognition performance. The aim of this paper is to evaluate the performance of different preprocessing techniques using transient information for gas identification from sensor array signals. We compare the classification accuracy of three feature extraction techniques based on steady state value, transient intergrals and dynamic slope. It was found that the transient information plays a critical role in improving the classification performance. In addition the proposed dynamic slope feature extraction technique is hardware friendly which makes the prospect of building a smart gas sensor very promising.

Original languageEnglish
Title of host publicationIEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering
VolumeA
Publication statusPublished - 2004
Externally publishedYes
EventIEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering - Chiang Mai, Thailand
Duration: 21 Nov 200424 Nov 2004

Other

OtherIEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering
CountryThailand
CityChiang Mai
Period21/11/0424/11/04

Fingerprint

Chemical sensors
Microelectronics
Feature extraction
Gases
Pattern recognition systems
Smart sensors
Sensor arrays
Hardware

Keywords

  • Classification
  • Gas sensor array
  • Pattern recognition
  • Preprocessing techniques

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Brahim-Belhouari, S., Bermak, A., Wei, G., & Chan, P. C. H. (2004). On the use of the transient information for gas identification using microelectronic gas sensor. In IEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering (Vol. A)

On the use of the transient information for gas identification using microelectronic gas sensor. / Brahim-Belhouari, Sofiane; Bermak, Amine; Wei, Guangfen; Chan, Philip C H.

IEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering. Vol. A 2004.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Brahim-Belhouari, S, Bermak, A, Wei, G & Chan, PCH 2004, On the use of the transient information for gas identification using microelectronic gas sensor. in IEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering. vol. A, IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering, Chiang Mai, Thailand, 21/11/04.
Brahim-Belhouari S, Bermak A, Wei G, Chan PCH. On the use of the transient information for gas identification using microelectronic gas sensor. In IEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering. Vol. A. 2004
Brahim-Belhouari, Sofiane ; Bermak, Amine ; Wei, Guangfen ; Chan, Philip C H. / On the use of the transient information for gas identification using microelectronic gas sensor. IEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering. Vol. A 2004.
@inproceedings{37138819b36e4a86b53f9967aac4a900,
title = "On the use of the transient information for gas identification using microelectronic gas sensor",
abstract = "Gas identification using microelectronic gas sensor represents a big challenge for pattern recognition systems due to a number of problems mainly related to non-selectivity and the drift. The use of preprocessing can often greatly improve the recognition performance. The aim of this paper is to evaluate the performance of different preprocessing techniques using transient information for gas identification from sensor array signals. We compare the classification accuracy of three feature extraction techniques based on steady state value, transient intergrals and dynamic slope. It was found that the transient information plays a critical role in improving the classification performance. In addition the proposed dynamic slope feature extraction technique is hardware friendly which makes the prospect of building a smart gas sensor very promising.",
keywords = "Classification, Gas sensor array, Pattern recognition, Preprocessing techniques",
author = "Sofiane Brahim-Belhouari and Amine Bermak and Guangfen Wei and Chan, {Philip C H}",
year = "2004",
language = "English",
volume = "A",
booktitle = "IEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering",

}

TY - GEN

T1 - On the use of the transient information for gas identification using microelectronic gas sensor

AU - Brahim-Belhouari, Sofiane

AU - Bermak, Amine

AU - Wei, Guangfen

AU - Chan, Philip C H

PY - 2004

Y1 - 2004

N2 - Gas identification using microelectronic gas sensor represents a big challenge for pattern recognition systems due to a number of problems mainly related to non-selectivity and the drift. The use of preprocessing can often greatly improve the recognition performance. The aim of this paper is to evaluate the performance of different preprocessing techniques using transient information for gas identification from sensor array signals. We compare the classification accuracy of three feature extraction techniques based on steady state value, transient intergrals and dynamic slope. It was found that the transient information plays a critical role in improving the classification performance. In addition the proposed dynamic slope feature extraction technique is hardware friendly which makes the prospect of building a smart gas sensor very promising.

AB - Gas identification using microelectronic gas sensor represents a big challenge for pattern recognition systems due to a number of problems mainly related to non-selectivity and the drift. The use of preprocessing can often greatly improve the recognition performance. The aim of this paper is to evaluate the performance of different preprocessing techniques using transient information for gas identification from sensor array signals. We compare the classification accuracy of three feature extraction techniques based on steady state value, transient intergrals and dynamic slope. It was found that the transient information plays a critical role in improving the classification performance. In addition the proposed dynamic slope feature extraction technique is hardware friendly which makes the prospect of building a smart gas sensor very promising.

KW - Classification

KW - Gas sensor array

KW - Pattern recognition

KW - Preprocessing techniques

UR - http://www.scopus.com/inward/record.url?scp=27944442026&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27944442026&partnerID=8YFLogxK

M3 - Conference contribution

VL - A

BT - IEEE TENCON 2004 - 2004 IEEE Region 10 Conference Proceedings: Analog and Digital Techniques in Electrical Engineering

ER -